[torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
Luka Govedič
2025-06-12 08:31:04 -07:00
committed by GitHub
co-authored by Sage Moore
parent 96846bb360
commit f98548b9da
33 changed files with 622 additions and 79 deletions
+1 -1
View File
@@ -15,7 +15,7 @@ if TYPE_CHECKING:
VLLM_RINGBUFFER_WARNING_INTERVAL: int = 60
VLLM_NCCL_SO_PATH: Optional[str] = None
LD_LIBRARY_PATH: Optional[str] = None
VLLM_USE_TRITON_FLASH_ATTN: bool = False
VLLM_USE_TRITON_FLASH_ATTN: bool = True
VLLM_V1_USE_PREFILL_DECODE_ATTENTION: bool = False
VLLM_FLASH_ATTN_VERSION: Optional[int] = None
LOCAL_RANK: int = 0